Graph network surrogate model for subsurface flow optimization

DOI10.1016/J.JCP.2024.113132MaRDI QIDQ6560712zbMATH OpenFDO

Authors Haoyu Tang, L. J. Durlofsky

Publication date 23 June 2024

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2024.113132

zbMATH Keywords

deep learning surrogategraph neural networkreservoir simulationsubsurface flowwell placement and control optimization

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Flows in porous media; filtration; seepage (76Sxx) Geophysics (86Axx)

Cites work

• An Introduction to Reservoir Simulation Using MATLAB/GNU Octave
• Conditioning generative adversarial networks on nonlinear data for subsurface flow model calibration and uncertainty quantification
• Convolutional -- recurrent neural network proxy for robust optimization and closed-loop reservoir management
• Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology
• Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
• Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks
• Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network
• Use of low-fidelity models with machine-learning error correction for well placement optimization

This page was built for publication: Graph network surrogate model for subsurface flow optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6560712)